INDEX

Explanations

statements relating to historical events and entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arten

-0.16

IDD

-0.15

oppins

-0.14

çĲ³

-0.14

adders

-0.14

arn

-0.14

ULER

-0.14

ect

-0.14

 intervening

-0.14

POSITIVE LOGITS

 oleh

0.16

by

0.15

 przez

0.14

/is

0.14

rup

0.14

flater

0.14

owing

0.14

 ØªÙĪØ³Ø·

0.14

amel

0.14

èĥŀ

0.14

Activations Density 0.023%

statements relating to historical events and entities

No Comments

No Known Activations